[go: up one dir, main page]

WO2025019536A3 - Modifying source data to generate hyperreal synthetic content - Google Patents

Modifying source data to generate hyperreal synthetic content Download PDF

Info

Publication number
WO2025019536A3
WO2025019536A3 PCT/US2024/038296 US2024038296W WO2025019536A3 WO 2025019536 A3 WO2025019536 A3 WO 2025019536A3 US 2024038296 W US2024038296 W US 2024038296W WO 2025019536 A3 WO2025019536 A3 WO 2025019536A3
Authority
WO
WIPO (PCT)
Prior art keywords
body part
generate
source data
hyperreal
synthetic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/US2024/038296
Other languages
French (fr)
Other versions
WO2025019536A2 (en
Inventor
Chris Ume
Jo Plaete
Martin Adams
Thomas Graham
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Metaphysic Ai
Original Assignee
Metaphysic Ai
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Metaphysic Ai filed Critical Metaphysic Ai
Publication of WO2025019536A2 publication Critical patent/WO2025019536A2/en
Publication of WO2025019536A3 publication Critical patent/WO2025019536A3/en
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

Modifying source data to generate hyperreal synthetic content is described. Source data representing images of a body part of a subject may be modified to obtain training data, such as by modifying the body part in the images and/or by enhancing the images to improve the quality thereof. One or more machine learning models may be trained using the training data to obtain one or more trained machine learning models, and the trained model(s) is used to generate output data representing a synthetic body part based at least in part on input data representing an image featuring the body part of the subject, such as an image featuring the modified body part and/or an enhanced image featuring the body part. The output data is then used to generate media data corresponding to media content featuring the synthetic body part.
PCT/US2024/038296 2023-07-17 2024-07-17 Modifying source data to generate hyperreal synthetic content Pending WO2025019536A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US18/353,608 2023-07-17
US18/353,608 US20250029208A1 (en) 2023-07-17 2023-07-17 Modifying source data to generate hyperreal synthetic content

Publications (2)

Publication Number Publication Date
WO2025019536A2 WO2025019536A2 (en) 2025-01-23
WO2025019536A3 true WO2025019536A3 (en) 2025-04-03

Family

ID=94260204

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2024/038296 Pending WO2025019536A2 (en) 2023-07-17 2024-07-17 Modifying source data to generate hyperreal synthetic content

Country Status (2)

Country Link
US (1) US20250029208A1 (en)
WO (1) WO2025019536A2 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200334867A1 (en) * 2018-01-29 2020-10-22 Microsft Tecchnology Licensing, LLC Face synthesis
US20210375020A1 (en) * 2020-01-03 2021-12-02 Vangogh Imaging, Inc. Remote visualization of real-time three-dimensional (3d) facial animation with synchronized voice
US20230066716A1 (en) * 2020-07-03 2023-03-02 Tencent Technology (Shenzhen) Company Limited Video generation method and apparatus, storage medium, and computer device
US20230215216A1 (en) * 2022-09-30 2023-07-06 Suprema AI Inc. Method for predicting characteristic information of target to be recognized, method for training neural network predicting characteristic information of target to be recognized, and computer-readable storage medium storing instructions to perform neural network training method
US20240212249A1 (en) * 2022-12-27 2024-06-27 Metaphysic.AI Latent space editing and neural animation to generate hyperreal synthetic faces

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8687880B2 (en) * 2012-03-20 2014-04-01 Microsoft Corporation Real time head pose estimation
US10586111B2 (en) * 2017-01-13 2020-03-10 Google Llc Using machine learning to detect which part of the screen includes embedded frames of an uploaded video
US10552977B1 (en) * 2017-04-18 2020-02-04 Twitter, Inc. Fast face-morphing using neural networks
CN110084193B (en) * 2019-04-26 2023-04-18 深圳市腾讯计算机系统有限公司 Data processing method, apparatus, and medium for face image generation
US10958874B2 (en) * 2019-05-09 2021-03-23 Present Communications, Inc. Video conferencing method
CN111275057B (en) * 2020-02-13 2023-06-20 腾讯科技（深圳）有限公司 Image processing method, device and equipment
US11354846B2 (en) * 2020-05-04 2022-06-07 Microsoft Technology Licensing, Llc Computing photorealistic versions of synthetic images
US11810397B2 (en) * 2020-08-18 2023-11-07 Samsung Electronics Co., Ltd. Method and apparatus with facial image generating
US11222466B1 (en) * 2020-09-30 2022-01-11 Disney Enterprises, Inc. Three-dimensional geometry-based models for changing facial identities in video frames and images
US11354774B2 (en) * 2020-10-06 2022-06-07 Unity Technologies Sf Facial model mapping with a neural network trained on varying levels of detail of facial scans
US12333427B2 (en) * 2020-10-16 2025-06-17 Adobe Inc. Multi-scale output techniques for generative adversarial networks
CN112287852B (en) * 2020-11-02 2023-11-21 腾讯科技（深圳）有限公司 Face image processing method, face image display method, face image processing device and face image display equipment
EP4044120A1 (en) * 2021-02-15 2022-08-17 Koninklijke Philips N.V. Training data synthesizer for contrast enhancing machine learning systems
US12111880B2 (en) * 2021-05-20 2024-10-08 Disney Enterprises, Inc. Face swapping with neural network-based geometry refining
US11398255B1 (en) * 2021-05-26 2022-07-26 Flawless Holdings Limited Modification of objects in film
DE112022002079T5 (en) * 2021-05-28 2024-01-25 Nvidia Corporation HIGH-PRECISION SEMANTIC IMAGE EDITING USING NEURONAL NETWORKS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS
CN113808277B (en) * 2021-11-05 2023-07-18 腾讯科技（深圳）有限公司 Image processing method and related device
US12299896B1 (en) * 2022-03-23 2025-05-13 Amazon Technologies, Inc. Synthetic image generation by manifold modification of a machine learning model
US12277738B2 (en) * 2022-03-29 2025-04-15 Lucasfilm Entertainment Company Ltd. LLC Method and system for latent-space facial feature editing in deep learning based face swapping
US12277696B2 (en) * 2022-04-08 2025-04-15 Robert Bosch Gmbh Data augmentation for domain generalization
US12374009B2 (en) * 2022-09-07 2025-07-29 Disney Enterprises, Inc. Multi-camera face swapping
CN115393183B (en) * 2022-10-28 2023-02-07 腾讯科技（深圳）有限公司 Image editing method and device, computer equipment and storage medium
EP4465210A1 (en) * 2023-05-19 2024-11-20 Robert Bosch GmbH Device and computer implemented method for determining a link in a knowledge graph
US20240404128A1 (en) * 2023-06-01 2024-12-05 Siemens Medical Solutions Usa, Inc. Methods and apparatus for synthetic computed tomography image generation
US20240420286A1 (en) * 2023-06-13 2024-12-19 Deep Voodoo, LLC Real-time augmentation of a plurality of target faces
US20250209707A1 (en) * 2023-12-26 2025-06-26 Netflix, Inc. Techniques for generating dubbed media content items

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200334867A1 (en) * 2018-01-29 2020-10-22 Microsft Tecchnology Licensing, LLC Face synthesis
US20210375020A1 (en) * 2020-01-03 2021-12-02 Vangogh Imaging, Inc. Remote visualization of real-time three-dimensional (3d) facial animation with synchronized voice
US20230066716A1 (en) * 2020-07-03 2023-03-02 Tencent Technology (Shenzhen) Company Limited Video generation method and apparatus, storage medium, and computer device
US20230215216A1 (en) * 2022-09-30 2023-07-06 Suprema AI Inc. Method for predicting characteristic information of target to be recognized, method for training neural network predicting characteristic information of target to be recognized, and computer-readable storage medium storing instructions to perform neural network training method
US20240212249A1 (en) * 2022-12-27 2024-06-27 Metaphysic.AI Latent space editing and neural animation to generate hyperreal synthetic faces

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MINCHUL KIM; FENG LIU; ANIL JAIN; XIAOMING LIU: "DCFace: Synthetic Face Generation with Dual Condition Diffusion Model", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 14 April 2023 (2023-04-14), 201 Olin Library Cornell University Ithaca, NY 14853, XP091484575 *

Also Published As

Publication number Publication date
US20250029208A1 (en) 2025-01-23
WO2025019536A2 (en) 2025-01-23

Similar Documents

Publication Publication Date Title
Dalim et al. TeachAR: An interactive augmented reality tool for teaching basic English to non-native children
EP3846109A3 (en) Method and apparatus for training online prediction model, device and storage medium
CN115294427B (en) A Stylized Image Description Generation Method Based on Transfer Learning
WO2023126914A3 (en) METHOD AND SYSTEM FOR SEMANTIC APPEARANCE TRANSFER USING SPLICING ViT FEATURES
WO2024159082A3 (en) Monocular depth and optical flow estimation using diffusion models
EP4123572A3 (en) An apparatus and a method for x-ray image restoration
CN104881853A (en) Skin color rectification method and system based on color conceptualization
EP3920094A3 (en) Method and apparatus for updating user image recognition model
EP4439446A3 (en) Electronic apparatus and control method thereof
CN110413551B (en) Information processing apparatus, method and device
WO2025019536A3 (en) Modifying source data to generate hyperreal synthetic content
CN117456064A (en) Method and system for rapidly generating intelligent companion based on photo and short audio
JPWO2021166129A5 (en)
MX2024007226A (en) Machine learning techniques for component-based image preprocessing.
Yang Study on the construction of multimodal interactive oral English teaching model
CN118898257B (en) Method and system for generating personalized question-answering large language model
CN111145316A (en) Teaching animation production system
Chen et al. New enhancement techniques for optimizing multimedia visual representations in music pedagogy
CN101409022A (en) Language learning system and method with mouth shape comparison
CN109933762A (en) Courseware making method, device, equipment and storage medium
Ding Application of Computer Science Technology in Foods Teaching
CN115455230A (en) Dance generation method and system
CN112668369A (en) Facial expression recognition method based on deep learning
WO2025188825A8 (en) Deep learning enabled segmentation of medical images with missing modalities
JP2024152811A5 (en)

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24843880

Country of ref document: EP

Kind code of ref document: A2